Trojans and Adversarial Examples: A Lethal Combination

2021-01-01 · Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Hai Phan

In this work, we naturally unify adversarial examples and Trojan backdoors into a new stealthy attack, that is activated only when 1) adversarial perturbation is injected into the input examples and 2) a Trojan backdoor is used to poison the training process simultaneously. Different from traditional attacks, we leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, thus making it difficult to be detected. Our attack can fool the user into accidentally trusting the infected model as a robust classifier against adversarial examples. We perform a thorough analysis and conduct an extensive set of experiments on several benchmark datasets to show that our attack can bypass existing defenses with a success rate close to 100%.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space

2023-04-02 · Yuwei Sun, Hideya Ochiai, Jun Sakuma

Trojan attacks embed perturbations in input data leading to malicious behavior in neural network models. A combination of various Trojans in different modalities enables an adversary to mount a sophisticated attack on mu…

Question Answering Visual Question Answering Visual Question Answering (VQA)

Improving Hierarchical Adversarial Robustness of Deep Neural Networks

2021-02-17 · Avery Ma, Aladin Virmaux, Kevin Scaman, Juwei Lu

Do all adversarial examples have the same consequences? An autonomous driving system misclassifying a pedestrian as a car may induce a far more dangerous -- and even potentially lethal -- behavior than, for instance, a c…

Adversarial Defense Adversarial Robustness Autonomous Driving General Classification

Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code

2024-08-22 · Mahdi Kazemi, Aftab Hussain, Md Rafiqul Islam Rabin, Mohammad Amin Alipour 외

This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs) and large language models of code (Cod…

Defect Detection Machine Unlearning Sentiment Analysis

Uncertainty-Aware Hardware Trojan Detection Using Multimodal Deep Learning

2024-01-15 · Rahul Vishwakarma, Amin Rezaei

The risk of hardware Trojans being inserted at various stages of chip production has increased in a zero-trust fabless era. To counter this, various machine learning solutions have been developed for the detection of har…

Decision Making Deep Learning Multimodal Deep Learning Uncertainty Quantification

SPICED: Syntactical Bug and Trojan Pattern Identification in A/MS Circuits using LLM-Enhanced Detection

2024-08-25 · Jayeeta Chaudhuri, Dhruv Thapar, Arjun Chaudhuri, Farshad Firouzi 외

Analog and mixed-signal (A/MS) integrated circuits (ICs) are crucial in modern electronics, playing key roles in signal processing, amplification, sensing, and power management. Many IC companies outsource manufacturing …

Anomaly Detection Language Modelling Large Language Model